Group 14 - Project FP01¶

Time series anomaly detection - Autoencoder¶

In [ ]:
import time
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import tensorflow as tf

from dataset import *
from plots import *
from metrics import *
from models_functions import *

# Set style for matplotlib
plt.style.use("Solarize_Light2")

import plotly.io as pio
pio.renderers.default = "notebook_connected"
WARNING:tensorflow:From c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.

In [ ]:
# Path to the root directory of the dataset
ROOTDIR_DATASET_NORMAL =  '../dataset/normal'
ROOTDIR_DATASET_ANOMALY = '../dataset/collisions'

# TF_ENABLE_ONEDNN_OPTS=0 means that the model will not use the oneDNN library for optimization

import os
os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'

Various parameters¶

In [ ]:
#freq = '1.0'
#freq = '0.1'
#freq = '0.01'
freq = '0.005'

file_name_normal = "_20220811_rbtc_"
file_name_collisions = "_collision_20220811_rbtc_"

recording_normal = [0, 2, 3, 4]
recording_collisions = [1, 5]

freq_str = freq.replace(".", "_")
features_folder_normal = f"./features/normal{freq_str}/"
features_folder_collisions = f"./features/collisions{freq_str}/"

Data¶

In [ ]:
df_features_normal, df_normal_raw, _ = get_dataframes(ROOTDIR_DATASET_NORMAL, file_name_normal, recording_normal, freq, None)
df_features_collisions, df_collisions_raw, df_collisions_raw_action = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, recording_collisions, freq, None)
df_features_collisions_1, df_collisions_raw_1, df_collisions_raw_action_1 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [1], freq, None)
df_features_collisions_5, df_collisions_raw_5, df_collisions_raw_action_5 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [5], freq, None)
Loading data.
Found 31 different actions.
Loading data done.

Computing features.

Progress: 0% Complete

0

Skipped feature extraction for pickFromPallet(1,2)=[true,1,0] 2022-08-11 14:37:37.436000 : 2022-08-11 14:37:37.421000.
Skipped feature extraction for placeToPallet(1,1)=[true,0] 2022-08-11 14:37:37.421000 : 2022-08-11 14:37:37.442000.
Skipped feature extraction for pickFromPallet(3,2)=[true,1,0] 2022-08-11 15:36:32.568000 : 2022-08-11 15:36:32.533000.
Skipped feature extraction for pickFromPallet(3,2)=[true,1,0] 2022-08-11 15:36:32.572000 : 2022-08-11 15:36:32.561000.
Skipped feature extraction for placeToPallet(1,3)=[true,0] 2022-08-11 15:36:32.533000 : 2022-08-11 15:36:32.572000.
Skipped feature extraction for placeToPallet(1,3)=[true,0] 2022-08-11 15:36:32.561000 : 2022-08-11 15:36:32.561000.
--- 115.43518686294556 seconds ---
Loading data.
Found 31 different actions.
Loading data done.

Computing features.

Progress: 0% Complete

0

Skipped feature extraction for moveOverPallet(1,3)=[true,0] 2022-08-11 16:55:15.149000 : 2022-08-11 16:55:15.146000.
Skipped feature extraction for moveOverPallet(3,1)=[true,0] 2022-08-11 16:55:15.146000 : 2022-08-11 16:55:15.150000.
--- 42.102439165115356 seconds ---
Loading data.
Found 31 different actions.
Loading data done.

Computing features.

Progress: 0% Complete

0

--- 23.57923984527588 seconds ---
Loading data.
Found 31 different actions.
Loading data done.

Computing features.

Progress: 0% Complete

0

Skipped feature extraction for moveOverPallet(1,3)=[true,0] 2022-08-11 16:55:15.149000 : 2022-08-11 16:55:15.146000.
Skipped feature extraction for moveOverPallet(3,1)=[true,0] 2022-08-11 16:55:15.146000 : 2022-08-11 16:55:15.150000.
--- 22.504485607147217 seconds ---
In [ ]:
# df_features_normal, df_normal_raw, _ = get_dataframes(ROOTDIR_DATASET_NORMAL, file_name_normal, recording_normal, freq, f"{features_folder_normal}")
# df_features_collisions, df_collisions_raw, df_collisions_raw_action = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, recording_collisions, freq, f"{features_folder_collisions}1_5/")
# df_features_collisions_1, df_collisions_raw_1, df_collisions_raw_action_1 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [1], freq, f"{features_folder_collisions}1/")
# df_features_collisions_5, df_collisions_raw_5, df_collisions_raw_action_5 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [5], freq, f"{features_folder_collisions}5/")
In [ ]:
X_train, y_train, X_test, y_test, df_test = get_train_test_data(df_features_normal, df_features_collisions, full_normal=True)
X_train_1, y_train_1, X_test_1, y_test_1, df_test_1 = get_train_test_data(df_features_normal, df_features_collisions_1, full_normal=True)
X_train_5, y_train_5, X_test_5, y_test_5, df_test_5 = get_train_test_data(df_features_normal, df_features_collisions_5, full_normal=True)

Collisions¶

In [ ]:
collisions_rec1, collisions_init1 = get_collisions('1', ROOTDIR_DATASET_ANOMALY)
collisions_rec5, collisions_init5 = get_collisions('5', ROOTDIR_DATASET_ANOMALY)

# Merge the collisions of the two recordings in one dataframe
collisions_rec = pd.concat([collisions_rec1, collisions_rec5])
collisions_init = pd.concat([collisions_init1, collisions_init5])
In [ ]:
collisions_zones, y_collisions = get_collisions_zones_and_labels(collisions_rec, collisions_init, df_features_collisions)
collisions_zones_1, y_collisions_1 = get_collisions_zones_and_labels(collisions_rec1, collisions_init1, df_features_collisions_1)
collisions_zones_5, y_collisions_5 = get_collisions_zones_and_labels(collisions_rec5, collisions_init5, df_features_collisions_5)

Autoencoder for Anomaly Detection in Time Series Data¶

In [ ]:
from algorithms.autoencoder import AutoEncoder

classifier = AutoEncoder(
    name='AutoEncoder',
    num_epochs=100,
    batch_size=32,
    lr=1e-3,
    hidden_size=32,
    sequence_length=5,
    train_gaussian_percentage=0.25,
    seed=42,
    gpu=None,
    details=True
)

# Train the AutoEncoder on normal data
classifier.fit(X_train)

print("AutoEncoder training completed.")
100%|██████████| 100/100 [00:19<00:00,  5.09it/s]
AutoEncoder training completed.

Predictions¶

In [ ]:
df_test = get_statistics(X_test, y_collisions, classifier, df_test, freq, threshold_type="mad")
df_test_1 = get_statistics(X_test_1, y_collisions_1, classifier, df_test_1, freq, threshold_type="mad")
df_test_5 = get_statistics(X_test_5, y_collisions_5, classifier, df_test_5, freq, threshold_type="mad")
Anomaly prediction completed.
Number of anomalies detected: 1 with threshold 20109904433.475876, std
Number of anomalies detected: 122 with threshold 315.33067339247657, mad
Number of anomalies detected: 16 with threshold 1840.3710062739015, percentile
Number of anomalies detected: 5 with threshold 2448.021878300716, IQR
Number of anomalies detected: 306 with threshold 0.0, zero

choosen threshold type: mad, with value: 315.3307
F1 Score: 0.8899
Accuracy: 0.9183
Precision: 0.8279
Recall: 0.9619
              precision    recall  f1-score   support

           0       0.98      0.90      0.94       201
           1       0.83      0.96      0.89       105

    accuracy                           0.92       306
   macro avg       0.90      0.93      0.91       306
weighted avg       0.93      0.92      0.92       306

ROC AUC Score: 0.9757
No description has been provided for this image
No description has been provided for this image
No description has been provided for this image
Anomalies detected: 122
Best threshold: 355.1155 | F1 Score: 0.8969 | Precision: 0.8475 | Recall: 0.9524
Anomalies detected with best threshold: 118

	-------------------------------------------------------------------------------------

Anomaly prediction completed.
Number of anomalies detected: 1 with threshold 27711242264.645176, std
Number of anomalies detected: 53 with threshold 172.04997223987004, mad
Number of anomalies detected: 9 with threshold 1484.1357438175683, percentile
Number of anomalies detected: 20 with threshold 739.9920483289995, IQR
Number of anomalies detected: 164 with threshold 0.0, zero

choosen threshold type: mad, with value: 172.0500
F1 Score: 0.7955
Accuracy: 0.8902
Precision: 0.6604
Recall: 1.0000
              precision    recall  f1-score   support

           0       1.00      0.86      0.93       129
           1       0.66      1.00      0.80        35

    accuracy                           0.89       164
   macro avg       0.83      0.93      0.86       164
weighted avg       0.93      0.89      0.90       164

ROC AUC Score: 0.9730
No description has been provided for this image
No description has been provided for this image
No description has been provided for this image
Anomalies detected: 53
Best threshold: 358.3724 | F1 Score: 0.8378 | Precision: 0.7949 | Recall: 0.8857
Anomalies detected with best threshold: 39

	-------------------------------------------------------------------------------------

Anomaly prediction completed.
Number of anomalies detected: 1 with threshold 2603.681733964626, std
Number of anomalies detected: 2 with threshold 2128.1909246378696, mad
Number of anomalies detected: 8 with threshold 1881.4748294474139, percentile
Number of anomalies detected: 1 with threshold 3102.3966379126678, IQR
Number of anomalies detected: 141 with threshold 0.0, zero

choosen threshold type: mad, with value: 2128.1909
F1 Score: 0.0690
Accuracy: 0.6170
Precision: 1.0000
Recall: 0.0357
              precision    recall  f1-score   support

           0       0.61      1.00      0.76        85
           1       1.00      0.04      0.07        56

    accuracy                           0.62       141
   macro avg       0.81      0.52      0.41       141
weighted avg       0.77      0.62      0.48       141

ROC AUC Score: 0.9393
No description has been provided for this image
No description has been provided for this image
No description has been provided for this image
Anomalies detected: 2
Best threshold: 864.6532 | F1 Score: 0.8800 | Precision: 0.7971 | Recall: 0.9821
Anomalies detected with best threshold: 69

	-------------------------------------------------------------------------------------

In [ ]:
plot_anomalies_true_and_predicted(df_collisions_raw, df_collisions_raw_action, collisions_zones, df_test, title="Collisions zones vs predicted zones for both recordings")
In [ ]:
plot_anomalies_true_and_predicted(df_collisions_raw_1, df_collisions_raw_action_1, collisions_zones_1, df_test_1, title="Collisions zones vs predicted zones for recording 1")
In [ ]:
plot_anomalies_true_and_predicted(df_collisions_raw_5, df_collisions_raw_action_5, collisions_zones_5, df_test_5, title="Collisions zones vs predicted zones for recording 5")